view contrib/undumprevlog @ 49520:eb02decdf0ab

dirstate-v2: skip evaluation of hgignore regex on cached directories

By making the computation of [has_ignored_ancestor] lazy we're eliding
its computation in the common case when none of its descendants have
changed on disk.

On a ~400k files repo, with a cached status, we saw a ~64% reduction
in CPU time, resulting in a speedup of ~10-15% (on ZFS), and a speedup
of ~38% of XFS (XFS has faster stat operations for some reason).

#!/usr/bin/env python3
# Undump a dump from dumprevlog
# $ hg init
# $ undumprevlog < repo.dump


import sys
from mercurial.node import bin
from mercurial import (
    encoding,
    revlog,
    transaction,
    vfs as vfsmod,
)
from mercurial.utils import procutil

from mercurial.revlogutils import (
    constants as revlog_constants,
)

for fp in (sys.stdin, sys.stdout, sys.stderr):
    procutil.setbinary(fp)

opener = vfsmod.vfs(b'.', False)
tr = transaction.transaction(
    sys.stderr.write, opener, {b'store': opener}, b"undump.journal"
)
while True:
    l = sys.stdin.readline()
    if not l:
        break
    if l.startswith("file:"):
        f = encoding.strtolocal(l[6:-1])
        assert f.endswith(b'.i')
        r = revlog.revlog(
            opener,
            target=(revlog_constants.KIND_OTHER, b'undump-revlog'),
            radix=f[:-2],
        )
        procutil.stdout.write(b'%s\n' % f)
    elif l.startswith("node:"):
        n = bin(l[6:-1])
    elif l.startswith("linkrev:"):
        lr = int(l[9:-1])
    elif l.startswith("parents:"):
        p = l[9:-1].split()
        p1 = bin(p[0])
        p2 = bin(p[1])
    elif l.startswith("length:"):
        length = int(l[8:-1])
        sys.stdin.readline()  # start marker
        d = encoding.strtolocal(sys.stdin.read(length))
        sys.stdin.readline()  # end marker
        r.addrevision(d, tr, lr, p1, p2)

tr.close()